© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14889
    Prev
    Next
    INDEX
    Explanations

    Blog tag, Inventory manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERICK
    -1.77
     or
    -1.70
    หรือ
    -1.70
     in
    -1.66
     celebrado
    -1.61
    ＆
    -1.55
     bekämp
    -1.52
    或者
    -1.51
    ･
    -1.48
    вает
    -1.47
    POSITIVE LOGITS
     the
    2.13
     usual
    1.71
    b
    1.70
     obt
    1.67
    </em>
    1.59
     USING
    1.48
    1.48
     our
    1.46
    </h6>
    1.45
    la
    1.45
    Activations Density 0.000%

    No Known Activations